INDEX

Explanations

references to identity, identification, and uncovering truths in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ivec

-0.15

Ã³mo

-0.15

adh

-0.14

eyh

-0.13

 å¦

-0.13

NSS

-0.13

 consid

-0.13

rana

-0.13

ad

-0.13

 strSql

-0.13

POSITIVE LOGITS

 identification

0.66

 identity

0.64

 Identification

0.60

 ident

0.59

 identify

0.59

 identities

0.57

 Identity

0.57

 Identify

0.57

 identified

0.54

identity

0.54

Activations Density 0.258%

references to identity, identification, and uncovering truths in various contexts

No Comments

No Known Activations