INDEX

Explanations

references to storage-related products and brands, especially in garage contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

<quote

-0.16

cec

-0.15

ExecutionContext

-0.15

ÐºÑĥÑĢ

-0.15

')?></

-0.14

.kr

-0.14

íĥģ

-0.14

 voksen

-0.14

ãģıãĤī

-0.14

ominator

-0.14

POSITIVE LOGITS

ima

0.15

urgeon

0.15

ream

0.15

lide

0.14

urre

0.14

 Grat

0.14

oral

0.14

BET

0.14

Activations Density 0.122%

references to storage-related products and brands, especially in garage contexts

No Comments

No Known Activations