INDEX

Explanations

personal names or proper nouns

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

agos

-0.15

#af

-0.14

isque

-0.14

$__

-0.14

ewolf

-0.14

outs

-0.14

und

-0.13

OutOfBoundsException

-0.13

hound

-0.13

.uni

-0.13

POSITIVE LOGITS

oday

0.15

iyel

0.14

_dependency

0.14

illos

0.13

iye

0.13

Ð³Ð°

0.13

èĨ

0.13

woke

0.13

 cort

0.12

Activations Density 0.146%

personal names or proper nouns

No Comments

No Known Activations