INDEX

Explanations

numerical information or data points in the text

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

akh

-0.16

punk

-0.15

iggers

-0.15

aks

-0.15

iaux

-0.14

ools

-0.14

ãĤ

-0.14

Âľ

-0.14

ponsive

-0.14

Ãºi

-0.14

POSITIVE LOGITS

ben

0.14

adiens

0.14

Ð¾Ñĩ

0.14

eeper

0.14

Ĥ¬

0.14

DDL

0.14

 æŁ

0.14

 bene

0.13

rint

0.13

PFN

0.13

Activations Density 0.005%

numerical information or data points in the text

No Comments

No Known Activations