INDEX

Explanations

references to guns and gun-related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ÐµÑĢÐ¸Ð½

-0.18

tte

-0.16

cue

-0.16

hid

-0.15

een

-0.15

crast

-0.15

cin

-0.15

hra

-0.15

gor

-0.15

AsStream

-0.15

POSITIVE LOGITS

pow

0.35

metal

0.27

ned

0.25

ning

0.25

ny

0.24

ners

0.24

shots

0.24

ner

0.23

boat

0.22

fight

0.22

Activations Density 0.024%

references to guns and gun-related terminology

No Comments

No Known Activations