INDEX

Explanations

references to user interactions, permissions, and operational capabilities

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

kee

-0.16

sta

-0.14

Bre

-0.14

unya

-0.13

 coinc

-0.13

ars

-0.13

iset

-0.13

elt

-0.13

en

-0.13

_SY

-0.13

POSITIVE LOGITS

 also

0.46

also

0.40

Also

0.38

 Also

0.38

 juga

0.34

 tambÃ©m

0.34

 tambiÃ©n

0.33

 ALSO

0.33

 ocksÃ¥

0.32

 cÅ©ng

0.32

Activations Density 0.192%

references to user interactions, permissions, and operational capabilities

No Comments

No Known Activations