INDEX

Explanations

elements related to notable events or functions within a narrative context, particularly focusing on significant terms like "bell," "law," and personal names associated with notable figures or memorials

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 predecess

-0.16

prav

-0.15

odash

-0.15

 desar

-0.15

ÅĦst

-0.15

lacak

-0.14

quiz

-0.14

beck

-0.14

AGO

-0.14

’ta

-0.13

POSITIVE LOGITS

_patterns

0.17

dam

0.16

 dams

0.16

IRT

0.16

0.15

 Silk

0.14

 Richt

0.14

al

0.14

 Scientist

0.14

precated

0.13

Activations Density 0.031%

elements related to notable events or functions within a narrative context, particularly focusing on significant terms like "bell," "law," and personal names associated with notable figures or memorials

No Comments

No Known Activations