INDEX

Explanations

nouns and their associated forms

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

 Flag

-0.17

ëĭ´

-0.16

ohn

-0.15

Ã¡no

-0.15

 Crest

-0.14

odel

-0.14

bpp

-0.14

igar

-0.14

arten

-0.14

idel

-0.13

POSITIVE LOGITS

_NATIVE

0.15

 coll

0.15

enza

0.14

.binary

0.14

/big

0.14

 casting

0.14

oll

0.14

doll

0.14

ÐµÐ½Ð·

0.13

los

0.13

Activations Density 0.034%

nouns and their associated forms

No Comments

No Known Activations