INDEX

Explanations

references to Columbia University

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

New Auto-Interp

Configuration

fnlp/Llama3_1-8B-Base-LXM-8x/Llama3_1-8B-Base-L22M-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.hook_mlp_out

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

rink

-0.16

ÑĢÐ°Ð±

-0.15

áº»

-0.15

Ä±rak

-0.14

ayar

-0.14

.ends

-0.14

uji

-0.14

VEC

-0.14

asco

-0.14

rms

-0.13

POSITIVE LOGITS

0.16

Liv

0.15

ÏĦÎ¹Î±

0.15

Iteration

0.14

 Deck

0.14

ATAL

0.14

Ð»Ð¸Ð²Ð°

0.14

Kun

0.14

unos

0.14

Erg

0.14

Activations Density 0.003%

references to Columbia University

No Comments

No Known Activations