INDEX

Explanations

terms related to scars and scar-related topics

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

ktop

-0.16

estr

-0.15

er

-0.15

atoi

-0.14

serter

-0.14

roke

-0.14

iating

-0.14

alli

-0.14

ocrisy

-0.14

 Exterior

-0.14

POSITIVE LOGITS

AREN

0.16

bid

0.15

cken

0.15

felt

0.15

ê¸Ī

0.14

MenuStrip

0.14

ENA

0.14

fv

0.14

ISP

0.14

Activations Density 0.014%

terms related to scars and scar-related topics

No Comments

No Known Activations