INDEX

Explanations

references to specific products or components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

-0.17

 seriousness

-0.16

ion

-0.16

izu

-0.16

-0.15

voke

-0.15

Shi

-0.15

ish

-0.14

emek

-0.14

POSITIVE LOGITS

ocs

0.15

_Anim

0.15

/includes

0.15

yat

0.15

#ab

0.15

 Phelps

0.15

Animations

0.14

_behavior

0.14

annis

0.14

ÑĪÑĮ

0.14

Activations Density 0.002%

references to specific products or components

No Comments

No Known Activations