INDEX

Explanations

phrases indicating distance or extent

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

icken

-0.16

Ø´ÙħØ§ÙĦÛĮ

-0.16

ifs

-0.15

oref

-0.15

oled

-0.15

ession

-0.15

roz

-0.15

ÏĨÎ¹

-0.14

/sm

-0.14

eker

-0.14

POSITIVE LOGITS

far

0.73

far

0.59

Far

0.53

Far

0.48

FAR

0.48

_far

0.47

 Ð´Ð°Ð»ÐµÐºÐ¾

0.42

 weit

0.38

è¿ľ

0.37

_FAR

0.37

Activations Density 0.067%

phrases indicating distance or extent

No Comments

No Known Activations