INDEX

Explanations

references to specific media entities, particularly names or acronyms associated with films or television shows

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 latter

-0.19

EGIN

-0.17

-0.16

ipherals

-0.16

IOD

-0.16

ector

-0.16

longleftrightarrow

-0.15

ighbor

-0.15

/or

-0.14

 habit

-0.14

POSITIVE LOGITS

odore

0.22

oload

0.18

WithValue

0.16

adays

0.15

olleyError

0.15

lez

0.14

amarin

0.14

shall

0.14

kÃ¶

0.14

onet

0.14

Activations Density 0.331%

references to specific media entities, particularly names or acronyms associated with films or television shows

No Comments

No Known Activations