INDEX

Explanations

words associated with enigmatic or mysterious topics and events

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

mans

-0.17

<↵

-0.14

haus

-0.14

erable

-0.13

 Trib

-0.13

reeNode

-0.13

 Treat

-0.13

 Martins

-0.13

ness

-0.13

nes

-0.13

POSITIVE LOGITS

rif

0.16

ute

0.15

oun

0.15

Ã¤nn

0.15

AREA

0.14

ummer

0.14

_prefs

0.14

rog

0.14

omor

0.14

-INF

0.14

Activations Density 0.001%

words associated with enigmatic or mysterious topics and events

No Comments

No Known Activations