INDEX

Explanations

references to public lands and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

Duy

-0.16

 desn

-0.16

istra

-0.16

theid

-0.15

ifen

-0.15

zers

-0.14

OPTION

-0.14

IVO

-0.14

å®¶ä¼Ļ

-0.14

à¸Ĥ

-0.14

POSITIVE LOGITS

0.17

iegel

0.16

lesi

0.15

[@

0.13

 mini

0.13

eniz

0.13

ure

0.13

å¤į

0.13

uppet

0.13

Activations Density 0.007%

references to public lands and related concepts

No Comments

No Known Activations