INDEX

Explanations

instances of published content or articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

Cha

-0.16

lix

-0.15

Cha

-0.15

eks

-0.14

_MAXIMUM

-0.14

enos

-0.14

ikipedia

-0.14

ube

-0.14

 Julien

-0.14

 Terrain

-0.14

POSITIVE LOGITS

Ð´Ñĥ

0.15

isti

0.15

azer

0.15

Äįka

0.15

 ValueEventListener

0.14

egal

0.14

arsi

0.13

lig

0.13

 mirrors

0.13

Activations Density 0.004%

instances of published content or articles

No Comments

No Known Activations