INDEX

Explanations

references to physical structures and buildings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

otta

-0.16

yy

-0.14

aises

-0.13

shop

-0.13

 Demon

-0.13

 policy

-0.13

éļ

-0.13

Fem

-0.13

ght

-0.13

olit

-0.13

POSITIVE LOGITS

YLON

0.16

 structure

0.15

structure

0.15

etak

0.14

vern

0.14

 trailers

0.14

å£Ĭ

0.14

DEC

0.14

aus

0.14

 LIABILITY

0.14

Activations Density 0.175%

references to physical structures and buildings

No Comments

No Known Activations