INDEX

Explanations

occurrences of the word "listed" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ongan

-0.16

ures

-0.16

gren

-0.15

sar

-0.15

_DL

-0.15

andra

-0.14

got

-0.14

Ãį

-0.14

oken

-0.14

ors

-0.14

POSITIVE LOGITS

 under

0.18

è¾°

0.17

iese

0.16

 abaixo

0.16

activex

0.16

 ÑģÑĢÐµÐ´Ð¸

0.15

anÃ©

0.15

redient

0.15

under

0.15

 alongside

0.15

Activations Density 0.032%

occurrences of the word "listed" and its variations

No Comments

No Known Activations