INDEX

Explanations

negative sentiments or expressions of doubt and resistance in contexts of social or personal dynamics

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

abar

-0.17

PURE

-0.15

åģ¥

-0.15

 Giov

-0.15

Bik

-0.14

ancell

-0.14

shint

-0.14

Î¼ÎŃÎ½

-0.13

ntl

-0.13

iggins

-0.13

POSITIVE LOGITS

nor

0.19

 fore

0.15

bout

0.15

Nor

0.15

Nor

0.14

ÃŃcia

0.14

lef

0.14

reak

0.14

gesch

0.14

_HIDE

0.14

Activations Density 0.583%

negative sentiments or expressions of doubt and resistance in contexts of social or personal dynamics

No Comments

No Known Activations