INDEX

Explanations

instances of the word "print" and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

-0.15

uter

-0.15

/problem

-0.15

 principal

-0.15

 principle

-0.15

principal

-0.15

er

-0.14

ules

-0.14

ats

-0.14

POSITIVE LOGITS

outs

0.20

erset

0.17

angible

0.16

ÏĦÎ¿Î¼Î±

0.16

Äįka

0.16

OrUpdate

0.15

iminal

0.15

igious

0.15

igy

0.15

making

0.15

Activations Density 0.030%

instances of the word "print" and related terms

No Comments

No Known Activations