INDEX

Explanations

references to best practices in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ady

-0.16

isor

-0.15

ookie

-0.14

Suc

-0.14

Suc

-0.14

ouv

-0.14

 vere

-0.14

ccion

-0.14

ohan

-0.14

nut

-0.14

POSITIVE LOGITS

é©

0.17

avel

0.17

bash

0.15

feit

0.15

fully

0.15

heets

0.14

ries

0.14

otas

0.14

 DÄĽ

0.13

Activations Density 0.012%

references to best practices in various contexts

No Comments

No Known Activations