INDEX

Explanations

proper nouns, specifically names and geographic locations

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

arkan

-0.17

ÐµÑĢÑĤÐ¸

-0.16

gree

-0.15

oproject

-0.15

ÏģÎ³

-0.14

 shemale

-0.14

quirer

-0.14

Hra

-0.14

ÙĪØŃ

-0.14

lesia

-0.14

POSITIVE LOGITS

datable

0.16

eny

0.15

antz

0.15

 burned

0.15

 concent

0.14

printf

0.14

èļ

0.14

ior

0.13

Activations Density 0.076%

proper nouns, specifically names and geographic locations

No Comments

No Known Activations