INDEX

Explanations

references to societal themes and discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

PD

-0.16

ext

-0.15

-0.14

pd

-0.14

abelle

-0.14

ather

-0.14

 Tight

-0.14

aise

-0.13

POSITIVE LOGITS

Rud

0.16

alah

0.15

hiba

0.15

venes

0.14

\Blueprint

0.14

idores

0.14

celed

0.14

FLT

0.14

ÏĥÎ¿

0.14

AZY

0.13

Activations Density 0.000%

references to societal themes and discussions

No Comments

No Known Activations