INDEX

Explanations

conjunctions and phrases indicating connection or relationship

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

Rag

-0.17

ington

-0.15

çļĦå¿ĥ

-0.15

dish

-0.15

 Minds

-0.15

ziel

-0.14

burgh

-0.14

ãģĭãģª

-0.14

lier

-0.14

uhn

-0.14

POSITIVE LOGITS

 selves

0.17

 approach

0.17

 ability

0.17

 abilities

0.16

 arsenal

0.14

oard

0.13

 ELSE

0.13

ickle

0.13

met

0.13

Ð¾ÑĢÐµ

0.13

Activations Density 0.136%

conjunctions and phrases indicating connection or relationship

No Comments

No Known Activations