INDEX

Explanations

mentions of specific individuals or notable figures

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

Ap

-0.15

AYOUT

-0.14

enuine

-0.14

_AX

-0.14

 Ø§Ùĩ

-0.14

 federally

-0.13

Ap

-0.13

lingen

-0.13

 Trie

-0.13

subst

-0.13

POSITIVE LOGITS

BBC

0.26

BBC

0.25

bbc

0.22

bbc

0.21

ITV

0.18

Capability

0.17

 Strict

0.17

 Sting

0.16

ÑĢÐ¾Ð¶

0.16

Ð¾Ð³Ñĥ

0.16

Activations Density 0.218%

mentions of specific individuals or notable figures

No Comments

No Known Activations