INDEX

Explanations

terms related to masking or filters in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

.mixin

-0.18

ndef

-0.16

ihat

-0.15

 Rosenstein

-0.15

lernen

-0.15

istically

-0.15

ADX

-0.15

asmus

-0.15

_EXTENDED

-0.14

ichten

-0.14

POSITIVE LOGITS

abella

0.16

ny

0.15

Æ°á»Ľ

0.15

rc

0.14

ric

0.14

lÃ¡n

0.14

ilden

0.14

ivet

0.14

oppers

0.14

Activations Density 0.003%

terms related to masking or filters in a technical context

No Comments

No Known Activations