INDEX

Explanations

words related to locking and unlocking mechanisms

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

hire

-0.15

åĳ½åĳ¨æľŁ

-0.15

maxlength

-0.15

Ã¤ch

-0.14

 Conserv

-0.14

£¨

-0.14

ngrx

-0.14

uddy

-0.14

nal

-0.14

inka

-0.14

POSITIVE LOGITS

mey

0.16

Ã¡bado

0.16

 bast

0.16

edException

0.16

ingly

0.15

sdale

0.15

0.14

tober

0.14

.acquire

0.14

Activations Density 0.012%

words related to locking and unlocking mechanisms

No Comments

No Known Activations