INDEX

Explanations

names of people involved in various contexts, particularly in sports and personal stories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

uddy

-0.15

bons

-0.14

 compar

-0.14

gow

-0.13

ud

-0.13

ichel

-0.13

agara

-0.13

esian

-0.12

cav

-0.12

ics

-0.12

POSITIVE LOGITS

visor

0.15

ables

0.14

ably

0.14

ful

0.14

dÃŃ

0.14

ngÃ¶r

0.13

underline

0.13

robe

0.13

lessly

0.13

_COOKIE

0.13

Activations Density 0.975%

names of people involved in various contexts, particularly in sports and personal stories

No Comments

No Known Activations