INDEX

Explanations

references to notable films or filmmakers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

/cgi

-0.17

itom

-0.15

pire

-0.14

airo

-0.14

marsh

-0.14

adge

-0.14

izr

-0.14

ÅĻ

-0.14

marker

-0.14

ugu

-0.14

POSITIVE LOGITS

/DD

0.15

anh

0.15

Net

0.14

adoo

0.14

Net

0.14

 Reform

0.14

.mit

0.14

dil

0.14

SSI

0.14

hes

0.13

Activations Density 0.393%

references to notable films or filmmakers

No Comments

No Known Activations