INDEX

Explanations

references to professional work and contributions of individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 rehe

-0.15

wf

-0.14

 Oval

-0.14

roller

-0.14

ROLLER

-0.13

askell

-0.13

Drawable

-0.13

 Virgin

-0.13

sink

-0.13

ãĥ³ãĥĪ

-0.13

POSITIVE LOGITS

enz

0.16

lessness

0.15

Ð°Ð½Ð¸ÑĨ

0.15

Ð°ÑĢÐ°Ð½

0.14

uras

0.13

amental

0.13

indsight

0.13

Ð»Ð¸

0.13

itel

0.13

elling

0.13

Activations Density 0.063%

references to professional work and contributions of individuals

No Comments

No Known Activations