INDEX

Explanations

superlatives indicating prominence or significance in a given context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

nie

-0.16

acic

-0.15

rego

-0.15

redo

-0.15

ÅĽnie

-0.14

baugh

-0.14

 Extras

-0.14

TypeEnum

-0.14

in

-0.14

coli

-0.14

POSITIVE LOGITS

ovu

0.14

NT

0.14

zi

0.14

Ø²Ø©

0.14

ale

0.14

chs

0.14

urtle

0.14

incinn

0.14

 Champ

0.13

 Christoph

0.13

Activations Density 0.087%

superlatives indicating prominence or significance in a given context

No Comments

No Known Activations