INDEX

Explanations

references to conferences and their associated details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

fully

-0.17

-0.15

ward

-0.15

Ø®Ø§ÙĨÙĩ

-0.15

red

-0.15

ern

-0.15

plash

-0.15

bars

-0.15

mes

-0.15

POSITIVE LOGITS

encing

0.15

ee

0.15

ional

0.15

vely

0.14

ãģĤãĤĬ

0.14

zimmer

0.14

PELL

0.14

ìķł

0.14

Ã©ment

0.14

yne

0.14

Activations Density 0.046%

references to conferences and their associated details

No Comments

No Known Activations