INDEX

Explanations

phrases that indicate requests or offers of information and assistance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

anut

-0.15

åĿĽ

-0.15

iox

-0.14

liner

-0.14

ForResource

-0.14

ãĤīãģĦ

-0.14

ÃĹ↵↵

-0.13

VML

-0.13

TRACE

-0.13

LineNumber

-0.13

POSITIVE LOGITS

 tell

0.57

åĳĬè¯ī

0.52

 telling

0.52

 tells

0.50

let

0.50

 Tell

0.50

Tell

0.50

tell

0.49

 inform

0.47

 letting

0.47

Activations Density 0.301%

phrases that indicate requests or offers of information and assistance

No Comments

No Known Activations