INDEX

Explanations

references to academic studies or scholarly research

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

uid

-0.15

bett

-0.14

dech

-0.14

roud

-0.14

lee

-0.14

USIC

-0.14

ottle

-0.14

xia

-0.14

ighton

-0.14

store

-0.14

POSITIVE LOGITS

lah

0.16

istica

0.14

ENA

0.14

elling

0.14

observeOn

0.14

ibraries

0.14

aniel

0.14

apur

0.14

çĢ¬

0.13

sol

0.13

Activations Density 0.036%

references to academic studies or scholarly research

No Comments

No Known Activations

references to academic studies or scholarly research

No Comments

No Known Activations