INDEX

Explanations

incidents involving violence and injury

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 Rough

-0.17

 rough

-0.15

ÐµÐ»ÐµÐ¼

-0.14

ouve

-0.14

statt

-0.14

Act

-0.14

cale

-0.14

 statistical

-0.14

combe

-0.14

haps

-0.13

POSITIVE LOGITS

hit

0.21

 shot

0.20

 bullet

0.20

shots

0.19

 hits

0.19

 Hits

0.19

-hit

0.19

Shot

0.18

shot

0.17

bullet

0.17

Activations Density 0.072%

incidents involving violence and injury

No Comments

No Known Activations