INDEX

Explanations

references to organizations and prominent figures associated with psychology and religion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

inx

-0.16

okie

-0.15

-0.14

unge

-0.14

umba

-0.14

ICAST

-0.14

imid

-0.13

Ð»ÑıÐ²

-0.13

IfExists

-0.13

 seats

-0.13

POSITIVE LOGITS

aho

0.17

/sys

0.15

_PROGRAM

0.14

Verb

0.14

asse

0.14

itom

0.13

 drum

0.13

-held

0.13

 refr

0.13

Activations Density 0.019%

references to organizations and prominent figures associated with psychology and religion

No Comments

No Known Activations