INDEX

Explanations

clauses that describe actions or changes involving a subject

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ULSE

-0.16

 Affero

-0.15

inded

-0.14

ÐµÑģÐ°

-0.14

","\

-0.14

%p

-0.14

mun

-0.14

Î½Î¿ÏĤ

-0.14

 AndAlso

-0.14

anagan

-0.14

POSITIVE LOGITS

 Wrong

0.16

ussy

0.16

bows

0.15

hue

0.14

APS

0.14

èª

0.14

antino

0.14

 ØªÙĤ

0.14

 anybody

0.14

 march

0.13

Activations Density 0.070%

clauses that describe actions or changes involving a subject

No Comments

No Known Activations