INDEX

Explanations

references to specific years in chronological order

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

erd

-0.21

andra

-0.15

indy

-0.14

.Preference

-0.14

anto

-0.14

azzi

-0.14

aku

-0.14

oso

-0.14

heads

-0.14

umpt

-0.14

POSITIVE LOGITS

kaar

0.18

anje

0.15

-toggler

0.15

Ľ°

0.14

uten

0.14

 fitte

0.14

-Sah

0.14

ULSE

0.14

 å²

0.13

Frameworks

0.13

Activations Density 0.006%

references to specific years in chronological order

No Comments

No Known Activations