INDEX

Explanations

names of individuals and proper nouns

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

ssa

-0.16

ephir

-0.14

ritel

-0.14

ollen

-0.13

ichten

-0.13

EmailAddress

-0.13

opsis

-0.13

ennai

-0.13

QN

-0.13

POSITIVE LOGITS

Ð¸ÑĨ

0.14

bol

0.14

iem

0.14

ow

0.14

anch

0.14

thouse

0.14

èªī

0.13

ë°į

0.13

amet

0.13

ilda

0.13

Activations Density 0.158%

names of individuals and proper nouns

No Comments

No Known Activations