INDEX

Explanations

references to locations or places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ists

-0.17

egan

-0.16

ucid

-0.16

adele

-0.15

ãĥ¼ãĥģ

-0.15

rape

-0.14

rael

-0.14

æ±Ĺ

-0.14

ande

-0.14

POSITIVE LOGITS

 where

0.24

ãģ§ãģ®

0.18

ê³³

0.18

_where

0.18

 waar

0.18

_compat

0.17

 oÃ¹

0.16

elin

0.15

 donde

0.15

elijke

0.15

Activations Density 0.035%

references to locations or places

No Comments

No Known Activations