INDEX

Explanations

references to consumers in various contexts

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

ÄĽ

-0.15

uluk

-0.15

orse

-0.15

nings

-0.14

 Cres

-0.14

ened

-0.14

olume

-0.14

iven

-0.13

enez

-0.13

POSITIVE LOGITS

lea

0.15

ographics

0.15

ulers

0.14

0.13

hear

0.13

ikan

0.13

ocol

0.13

FINAL

0.13

 accol

0.13

_equals

0.13

Activations Density 0.011%

references to consumers in various contexts

No Comments

No Known Activations