INDEX

Explanations

occurrences of the word "No" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

rik

-0.17

gh

-0.16

rent

-0.15

 æ©

-0.15

-ÑĤÐ¾

-0.15

ritis

-0.15

ycz

-0.15

patrick

-0.14

Ī¬

-0.14

rol

-0.14

POSITIVE LOGITS

xious

0.32

 longer

0.31

isy

0.27

veau

0.25

ises

0.25

zzle

0.24

 matter

0.24

 doubt

0.23

 Longer

0.23

things

0.23

Activations Density 0.120%

occurrences of the word "No" in various contexts

No Comments

No Known Activations