INDEX

Explanations

instances of the word "directed" related to film direction

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

mgr

-0.16

iren

-0.15

elves

-0.14

ynom

-0.14

 Hull

-0.14

Î´ÎµÏĤ

-0.14

eprom

-0.14

ocoder

-0.14

 Chad

-0.14

lian

-0.14

POSITIVE LOGITS

asso

0.15

achsen

0.14

Ø¯Ø§Ùħ

0.14

 loyalty

0.14

UY

0.14

enties

0.14

Fld

0.14

alent

0.14

 Russo

0.14

Activations Density 0.004%

instances of the word "directed" related to film direction

No Comments

No Known Activations