INDEX

Explanations

specific proper nouns, particularly names and affiliations related to research or publications

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

utenberg

-0.15

ullan

-0.15

uyen

-0.15

ivol

-0.14

elsea

-0.14

.mdl

-0.14

ToFile

-0.14

ÃŃme

-0.14

ãĤ¡

-0.14

.dense

-0.14

POSITIVE LOGITS

arg

0.16

ï¸

0.14

Arg

0.14

ÑĦÐ¸

0.14

 perfor

0.14

 Carrier

0.13

ãĥ¥

0.13

emies

0.13

.*,

0.13

biz

0.13

Activations Density 0.124%

specific proper nouns, particularly names and affiliations related to research or publications

No Comments

No Known Activations