INDEX

Explanations

terms related to community engagement and the sharing of information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

inger

-0.16

 certain

-0.16

tainment

-0.16

ombat

-0.15

 Certain

-0.15

igar

-0.14

esar

-0.14

iband

-0.14

Certain

-0.14

INGER

-0.14

POSITIVE LOGITS

 separate

0.30

 seperate

0.28

 Separate

0.27

 independent

0.26

 independ

0.26

çĭ¬ç«ĭ

0.26

 independently

0.25

 separation

0.25

 Separ

0.24

 separated

0.24

Activations Density 0.013%

terms related to community engagement and the sharing of information

No Comments

No Known Activations