INDEX

Explanations

references to 'people' and their opinions or behaviors

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

stadt

-0.15

erner

-0.15

nici

-0.14

venes

-0.13

uzu

-0.13

duk

-0.13

urga

-0.13

ocre

-0.13

ãģĿ

-0.13

udiantes

-0.13

POSITIVE LOGITS

rosso

0.18

ipo

0.16

 might

0.15

say

0.15

 forget

0.15

arus

0.15

Ðĭ

0.15

 talk

0.14

raud

0.14

Activations Density 0.088%

references to 'people' and their opinions or behaviors

No Comments

No Known Activations