INDEX

Explanations

references to identity and identification 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 @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

uter

-0.18

loe

-0.17

esse

-0.17

ÙĨØ´

-0.16

 Bundy

-0.16

argent

-0.15

antry

-0.14

athy

-0.14

ese

-0.14

 RequestMethod

-0.14

POSITIVE LOGITS

ENTITY

0.23

 crisis

0.22

 politics

0.21

 Crisis

0.20

 formation

0.20

 theft

0.20

formation

0.19

 crises

0.18

 Politics

0.18

ves

0.18

Activations Density 0.017%

references to identity and identification in various contexts

No Comments

No Known Activations