INDEX

Explanations

pronouns that refer to individuals or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ritz

-0.20

Ded

-0.17

erton

-0.17

ded

-0.17

 Fritz

-0.16

 Infer

-0.15

iors

-0.15

amba

-0.15

orden

-0.14

pty

-0.14

POSITIVE LOGITS

act

0.20

Act

0.19

 acting

0.17

 treat

0.17

 acted

0.17

act

0.16

 Acting

0.16

feel

0.15

 treated

0.15

 feel

0.15

Activations Density 0.000%

pronouns that refer to individuals or groups

No Comments

No Known Activations

pronouns that refer to individuals or groups

No Comments

No Known Activations