INDEX

Explanations

references to personal identity and related concepts

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

loe

-0.19

esse

-0.15

NC

-0.15

esian

-0.15

arget

-0.15

izona

-0.14

isman

-0.14

 ÑĤÑĢÑĥÐ´Ð°

-0.14

è®¸

-0.14

iar

-0.14

POSITIVE LOGITS

ENTITY

0.19

 theft

0.19

ponge

0.18

entities

0.17

(identity

0.17

zend

0.16

/disable

0.16

 Theft

0.16

 twin

0.15

 crisis

0.15

Activations Density 0.019%

references to personal identity and related concepts

No Comments

No Known Activations