INDEX

Explanations

references to specific individuals and their associated data in censuses

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

iyi

-0.16

 Barg

-0.16

ãĥªãĥ³

-0.15

nard

-0.15

áº«n

-0.14

riger

-0.14

imbus

-0.14

&e

-0.14

idine

-0.14

assen

-0.14

POSITIVE LOGITS

esk

0.15

es

0.14

/path

0.14

ned

0.14

iche

0.14

vac

0.14

@mail

0.14

 dent

0.13

Gol

0.13

Sah

0.13

Activations Density 0.001%

references to specific individuals and their associated data in censuses

No Comments

No Known Activations