INDEX

Explanations

identifiers and attributes 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 @ 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

igm

-0.16

ixmap

-0.15

iar

-0.14

inet

-0.14

iÅ¾

-0.14

Ã¹i

-0.14

UILTIN

-0.14

ãģªãģĮ

-0.13

onia

-0.13

POSITIVE LOGITS

elden

0.15

amen

0.15

 Gest

0.14

azen

0.14

 toll

0.14

ourcem

0.14

chner

0.14

Ã¤tze

0.14

zy

0.14

ÑĢÑĥÐ½

0.14

Activations Density 0.032%

identifiers and attributes of individuals

No Comments

No Known Activations