INDEX

Explanations

quotations and dialogue within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

sel

-0.19

å·»

-0.15

vol

-0.14

idis

-0.14

ÑĬ

-0.14

AuthProvider

-0.14

hips

-0.14

å°ĭ

-0.14

ä½

-0.14

athers

-0.13

POSITIVE LOGITS

ÂĿ

0.16

Https

0.16

amat

0.15

ollen

0.15

å¾®è½¯éĽħé»ĳ

0.15

ãĢģ“

0.15

 Weinstein

0.14

cken

0.14

åĲ§

0.14

-ie

0.14

Activations Density 0.085%

quotations and dialogue within the text

No Comments

No Known Activations