INDEX

Explanations

references to non-fiction and documentary styles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

egin

-0.15

ÅĤa

-0.15

insk

-0.15

akis

-0.14

Wrap

-0.14

arios

-0.14

AMENT

-0.14

phan

-0.14

æĹ¶ä»£

-0.14

addtogroup

-0.14

POSITIVE LOGITS

 Lips

0.16

orer

0.16

claimer

0.16

usting

0.15

 historical

0.15

imson

0.14

spi

0.14

ÙĨØ¯Ú¯ÛĮ

0.14

etin

0.14

Activations Density 0.020%

references to non-fiction and documentary styles

No Comments

No Known Activations