INDEX

Explanations

references to specific locations, particularly in Essex

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

endi

-0.16

oola

-0.16

bedo

-0.15

arty

-0.15

ande

-0.15

obus

-0.15

 slic

-0.14

nnen

-0.14

modifiable

-0.14

 crossorigin

-0.14

POSITIVE LOGITS

èĻŁ

0.14

ROWS

0.14

 Virgin

0.14

inite

0.14

\Mapping

0.13

 Inner

0.13

 Canary

0.13

-fr

0.13

ARAM

0.13

bote

0.13

Activations Density 0.075%

references to specific locations, particularly in Essex

No Comments

No Known Activations