INDEX

Explanations

references to landscapes in various forms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

olah

-0.18

dzi

-0.17

olest

-0.16

à¹Ģà¸ļ

-0.15

riad

-0.14

 Beste

-0.14

anced

-0.14

strand

-0.14

 cord

-0.13

à¹Ģà¸¥

-0.13

POSITIVE LOGITS

aler

0.17

all

0.16

armor

0.15

ael

0.15

 sequel

0.15

_FULLSCREEN

0.14

enthal

0.14

 Gall

0.14

ixe

0.14

Activations Density 0.007%

references to landscapes in various forms

No Comments

No Known Activations