INDEX

Explanations

names and identifiers related to individuals and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

izza

-0.19

izik

-0.16

zie

-0.16

rex

-0.16

èİ

-0.14

izzo

-0.14

vore

-0.14

inh

-0.14

sÃŃ

-0.14

cem

-0.13

POSITIVE LOGITS

().'/

0.16

0.15

dale

0.14

rane

0.14

 Manning

0.13

ento

0.13

adal

0.13

orp

0.13

oucher

0.13

IMS

0.13

Activations Density 0.006%

names and identifiers related to individuals and locations

No Comments

No Known Activations