INDEX

Explanations

instances of specific verbs and modifiers indicating actions or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ych

-0.15

 coli

-0.14

UBL

-0.14

InstantiationException

-0.14

 generations

-0.14

stitutions

-0.13

iam

-0.13

ej

-0.13

det

-0.13

Ã¼ck

-0.13

POSITIVE LOGITS

iets

0.15

ãĥ«ãĥī

0.14

hetto

0.14

isco

0.14

Fal

0.14

imson

0.14

 VerfÃ¼g

0.14

REATE

0.13

 NSIndexPath

0.13

 Realty

0.13

Activations Density 0.002%

instances of specific verbs and modifiers indicating actions or states

No Comments

No Known Activations