INDEX

Explanations

references to similarity and relationships between concepts or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

aden

-0.18

anh

-0.15

edom

-0.14

PILE

-0.13

upa

-0.13

adel

-0.13

ede

-0.13

modulo

-0.13

POSITIVE LOGITS

 YÃ¶n

0.16

aeper

0.14

fixed

0.14

enville

0.14

lao

0.14

 Abraham

0.14

 pÃ¡s

0.14

bir

0.14

angstrom

0.14

lotte

0.14

Activations Density 0.308%

references to similarity and relationships between concepts or entities

No Comments

No Known Activations