INDEX

Explanations

occurrences of the letter 'S' 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 @ 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

venile

-0.15

ugged

-0.14

cn

-0.14

agal

-0.14

ÙĪØ³Øª

-0.14

pow

-0.14

etrofit

-0.14

ledge

-0.14

 Airport

-0.13

ÐµÑı

-0.13

POSITIVE LOGITS

sz

0.15

BEL

0.15

enz

0.14

_FR

0.14

aus

0.14

iver

0.14

OptionPane

0.14

 Lies

0.14

Aus

0.13

ofi

0.13

Activations Density 0.013%

occurrences of the letter 'S' in various contexts

No Comments

No Known Activations