INDEX

Explanations

geographical locations and place names

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

etler

-0.14

à¸²à¸ķà¸£

-0.14

 treff

-0.14

reste

-0.14

 prostitut

-0.13

lep

-0.13

NotSupportedException

-0.13

reib

-0.13

udson

-0.13

.bunifuFlatButton

-0.13

POSITIVE LOGITS

 Cummings

0.15

 Lester

0.15

enia

0.14

post

0.14

iel

0.14

.pattern

0.13

Bon

0.13

 Cutter

0.13

av

0.13

ensing

0.13

Activations Density 0.217%

geographical locations and place names

No Comments

No Known Activations