INDEX

Explanations

references to system endpoints or connections in technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

erk

-0.16

ateau

-0.14

ouser

-0.14

aces

-0.14

utoff

-0.14

ibles

-0.13

udent

-0.13

ff

-0.13

abyrin

-0.13

ides

-0.13

POSITIVE LOGITS

REA

0.17

uala

0.14

alama

0.14

sect

0.14

escort

0.14

../../../

0.13

á»¥y

0.13

ura

0.13

.constructor

0.13

Activations Density 0.005%

references to system endpoints or connections in technical contexts

No Comments

No Known Activations