INDEX

Explanations

terms related to divisions, sections, or groupings within a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 directly

-0.17

 ranking

-0.15

prung

-0.15

lesh

-0.15

isay

-0.15

ids

-0.14

inski

-0.14

 margin

-0.14

ÑĢÐµÐ·

-0.14

POSITIVE LOGITS

 according

0.24

 into

0.21

according

0.20

ge

0.20

 Into

0.19

 According

0.18

 differently

0.18

into

0.18

 depending

0.17

 accordingly

0.17

Activations Density 0.094%

terms related to divisions, sections, or groupings within a text

No Comments

No Known Activations