INDEX

Explanations

references to anecdotal experiences and personal narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 Balk

-0.15

bach

-0.15

ucc

-0.15

ryn

-0.15

 Frank

-0.15

ings

-0.15

ucci

-0.15

.community

-0.15

ingles

-0.15

phia

-0.14

POSITIVE LOGITS

cket

0.17

Ã½t

0.15

amik

0.15

æĤŁ

0.15

claimer

0.15

getDisplay

0.15

.qt

0.14

akening

0.14

ä¹³

0.13

InitStruct

0.13

Activations Density 0.233%

references to anecdotal experiences and personal narratives

No Comments

No Known Activations