INDEX

Explanations

references to incidents involving explosions and fire

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

eÄį

-0.16

ockey

-0.16

 backpage

-0.15

aped

-0.15

isContained

-0.15

ëł´

-0.14

Ã¶g

-0.14

apgolly

-0.14

hq

-0.14

archive

-0.14

POSITIVE LOGITS

iks

0.16

 partnership

0.15

arr

0.14

 arrangement

0.14

flex

0.14

aten

0.14

atti

0.14

ics

0.14

long

0.14

illing

0.14

Activations Density 1.812%

references to incidents involving explosions and fire

No Comments

No Known Activations