INDEX

Explanations

phrases associated with symposia and conferences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

pend

-0.14

Ã³r

-0.14

edo

-0.14

reds

-0.14

 oversh

-0.14

åľ¨åľ°

-0.14

Nob

-0.14

 formal

-0.14

dont

-0.13

 ceremonial

-0.13

POSITIVE LOGITS

 Lumpur

0.15

izzard

0.15

-Clause

0.14

OnInit

0.14

psilon

0.14

anner

0.14

amiliar

0.13

ERGE

0.13

<Mesh

0.13

ewidth

0.13

Activations Density 0.085%

phrases associated with symposia and conferences

No Comments

No Known Activations