INDEX

Explanations

proper nouns and names in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lop

-0.13

ard

-0.13

 âĹĦ

-0.13

äº¡

-0.13

JNI

-0.13

pres

-0.13

erer

-0.13

oyal

-0.13

chy

-0.13

villa

-0.13

POSITIVE LOGITS

af

0.16

.gb

0.15

klÃ¤

0.15

0.14

èĨ

0.14

è±¡

0.14

 elev

0.13

baum

0.13

azu

0.13

Activations Density 0.132%

proper nouns and names in the text

No Comments

No Known Activations