INDEX

Explanations

references to forms and applications related to registration and documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 Collision

-0.16

 center

-0.15

 centre

-0.15

 finished

-0.15

 collision

-0.14

sm

-0.14

olit

-0.14

 Grain

-0.14

alat

-0.14

 fore

-0.14

POSITIVE LOGITS

NECT

0.15

urette

0.15

/stdc

0.14

itten

0.14

ÙĲØ±

0.14

ÏĥÏĦÏģÎ¿

0.14

oud

0.14

PCA

0.14

jiang

0.14

Leaks

0.14

Activations Density 0.066%

references to forms and applications related to registration and documentation

No Comments

No Known Activations