INDEX

Explanations

articles and quantifiers related to nouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

bows

-0.16

-0.15

ellig

-0.15

Pdf

-0.14

 Lester

-0.14

clerosis

-0.14

uala

-0.14

bow

-0.14

Pdf

-0.14

imdi

-0.13

POSITIVE LOGITS

æİ§

0.15

uckle

0.15

eh

0.15

.RGB

0.14

 ì¶Ķì²ľ

0.14

 crush

0.14

_MODULES

0.14

ibri

0.14

ico

0.14

rage

0.14

Activations Density 0.221%

articles and quantifiers related to nouns

No Comments

No Known Activations