INDEX

Explanations

the presence of key features or attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

alias

-0.16

-0.15

ordial

-0.14

ramer

-0.14

Bias

-0.14

iesz

-0.14

wargs

-0.13

panion

-0.13

 exponent

-0.13

oned

-0.13

POSITIVE LOGITS

ãĥģãĥ¥

0.17

frei

0.16

OMPI

0.15

 Hills

0.15

AdminController

0.14

 Spar

0.14

ãĥ©ãĤ¤ãĥ³

0.14

anja

0.14

ìķħ

0.14

okit

0.13

Activations Density 0.039%

the presence of key features or attributes

No Comments

No Known Activations

the presence of key features or attributes

No Comments

No Known Activations