INDEX

Explanations

names of individuals and references to people in various contexts

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

utex

-0.16

roud

-0.15

aticon

-0.14

ekk

-0.14

ãĢħ

-0.14

buz

-0.14

lassen

-0.14

ewan

-0.14

qus

-0.14

ahat

-0.13

POSITIVE LOGITS

 Column

0.15

aval

0.14

 aque

0.14

yx

0.14

 çİ

0.14

 Columns

0.14

°

0.14

 fitte

0.13

onde

0.13

 Prefix

0.13

Activations Density 0.028%

names of individuals and references to people in various contexts

No Comments

No Known Activations