INDEX

Explanations

proper nouns, particularly names and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

avern

-0.16

meli

-0.14

UIT

-0.14

sic

-0.13

ignon

-0.13

ertoire

-0.13

chio

-0.13

egie

-0.13

qus

-0.13

POSITIVE LOGITS

jas

0.21

sss

0.15

ê±¸

0.15

tsx

0.14

 chatt

0.14

ä¹±

0.14

aceae

0.13

Lex

0.13

 coll

0.13

Activations Density 0.039%

proper nouns, particularly names and locations

No Comments

No Known Activations