INDEX

Explanations

prominent nouns and verbs related to objects and actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

olver

-0.15

tractor

-0.15

à¥Įà¤¤

-0.14

 dokun

-0.14

$MESS

-0.14

rene

-0.13

privation

-0.13

atra

-0.13

Î¬Î»

-0.13

 Winchester

-0.13

POSITIVE LOGITS

 exhaust

0.17

ãĥ³ãĥĸ

0.16

 Exhaust

0.16

.EntityFramework

0.15

 live

0.15

 Live

0.15

 burning

0.14

icks

0.14

 lived

0.14

eron

0.14

Activations Density 0.006%

prominent nouns and verbs related to objects and actions

No Comments

No Known Activations