INDEX

Explanations

references to specific locations, institutions, and educational events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ichel

-0.16

ãģıãĤĵ

-0.16

ãĥķãĤ

-0.15

igy

-0.15

 stÅĻ

-0.14

 Ansi

-0.14

 Gang

-0.14

gang

-0.14

 gang

-0.14

adb

-0.14

POSITIVE LOGITS

 crystal

0.20

 crystals

0.17

 Structure

0.17

 refin

0.16

rod

0.16

 Crystal

0.15

 structure

0.15

 Structural

0.15

 refined

0.15

cr

0.14

Activations Density 0.010%

references to specific locations, institutions, and educational events

No Comments

No Known Activations