INDEX

Explanations

mentions of specific individuals' names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

osg

-0.17

é¡µéĿ¢åŃĺæ¡£å¤ĩä»½

-0.17

ModelProperty

-0.17

à¸Ļà¸²à¸Ķ

-0.16

antaged

-0.16

_mE

-0.16

Sez

-0.15

undra

-0.15

ubbo

-0.15

olland

-0.15

POSITIVE LOGITS

0.19

0.16

0.15

 Kendrick

0.15

Activations Density 0.005%

mentions of specific individuals' names

No Comments

No Known Activations