INDEX

Explanations

references to specific filmmakers and their works

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

idia

-0.15

ll

-0.15

 Grill

-0.15

abel

-0.14

Tub

-0.14

 whole

-0.14

 daily

-0.14

ifer

-0.14

POSITIVE LOGITS

 semiclass

0.17

,},↵

0.15

-gnu

0.15

LOPT

0.15

orny

0.15

ichert

0.15

 vlas

0.14

deme

0.14

.descriptor

0.14

vaz

0.14

Activations Density 0.133%

references to specific filmmakers and their works

No Comments

No Known Activations