INDEX

Explanations

instances of the word "for" and its variations in context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

Ø§Ø¨Ùĩ

-0.17

roman

-0.15

igung

-0.14

oci

-0.14

onet

-0.14

á¿¦

-0.14

lip

-0.14

yna

-0.14

ugu

-0.14

ViewById

-0.14

POSITIVE LOGITS

folio

0.15

kers

0.15

apter

0.15

çī

0.15

folios

0.14

ÑģÑĮ

0.14

.Tween

0.14

 BaseModel

0.14

esk

0.14

å±

0.14

Activations Density 0.173%

instances of the word "for" and its variations in context

No Comments

No Known Activations