INDEX

Explanations

references to the name 'Swan' and its variations

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

fect

-0.16

abit

-0.15

 unfinished

-0.15

ink

-0.15

LING

-0.15

ifice

-0.14

 crowds

-0.14

junction

-0.14

 Angeles

-0.13

exo

-0.13

POSITIVE LOGITS

ovie

0.17

ipple

0.14

Untitled

0.14

 Tale

0.14

egas

0.14

.FontStyle

0.14

ovich

0.14

ourt

0.14

avigation

0.14

etri

0.14

Activations Density 0.004%

references to the name 'Swan' and its variations

No Comments

No Known Activations