INDEX

Explanations

references to research findings or results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ASK

-0.16

ask

-0.15

ilia

-0.15

innen

-0.15

cheng

-0.14

İ

-0.14

akhir

-0.14

ÑĢÐ¾Ñĩ

-0.14

Ask

-0.14

iro

-0.14

POSITIVE LOGITS

ÏĢÎŃ

0.17

mlink

0.15

egas

0.15

SION

0.15

Capability

0.14

urst

0.14

.createFrom

0.14

ç£¨

0.14

 OTHERWISE

0.14

otherwise

0.14

Activations Density 0.010%

references to research findings or results

No Comments

No Known Activations