INDEX

Explanations

proper nouns, particularly names of people and locations, and references to specific actions or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

dorf

-0.15

 Î¹ÏĥÏĩ

-0.15

 à¤¨à¤Ĺà¤°

-0.15

å¥½çļĦ

-0.14

ÏĩÏī

-0.14

icers

-0.14

hesion

-0.14

sdk

-0.14

icies

-0.14

ottle

-0.14

POSITIVE LOGITS

 Strand

0.15

Jas

0.15

ando

0.14

><?

0.14

iko

0.14

 Coff

0.14

 Ãł

0.13

yum

0.13

 Acting

0.13

 Tone

0.13

Activations Density 0.407%

proper nouns, particularly names of people and locations, and references to specific actions or events

No Comments

No Known Activations