INDEX

Explanations

references to viruses or viral phenomena

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

tram

-0.16

ennes

-0.16

vice

-0.15

lug

-0.15

artment

-0.15

ibold

-0.15

Ð½Ð°ÑĢ

-0.15

clared

-0.15

serrat

-0.14

edo

-0.14

POSITIVE LOGITS

udeau

0.18

aso

0.16

ayo

0.15

TRL

0.14

utherford

0.14

imals

0.14

è²

0.14

asso

0.14

airo

0.14

istro

0.14

Activations Density 0.007%

references to viruses or viral phenomena

No Comments

No Known Activations