INDEX

Explanations

references to navigation or pagination in content

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

_DIGEST

-0.15

hos

-0.14

·»

-0.14

æĳĺ

-0.13

 lign

-0.13

hong

-0.13

wo

-0.13

 Leban

-0.13

iais

-0.13

enheim

-0.13

POSITIVE LOGITS

endale

0.15

_HW

0.15

_CID

0.15

HEET

0.14

chter

0.14

VERR

0.14

/Runtime

0.14

@qq

0.14

 pockets

0.13

_Renderer

0.13

Activations Density 0.006%

references to navigation or pagination in content

No Comments

No Known Activations