INDEX

Explanations

references to decorative elements or features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ANEL

-0.15

icia

-0.15

upo

-0.14

oÅĻ

-0.14

Î³Î¬

-0.14

iena

-0.14

ondheim

-0.14

ekk

-0.14

anni

-0.14

amin

-0.14

POSITIVE LOGITS

afa

0.18

ally

0.17

orra

0.16

als

0.15

all

0.15

eo

0.15

 borr

0.14

tion

0.14

strategy

0.14

tal

0.14

Activations Density 0.003%

references to decorative elements or features

No Comments

No Known Activations