INDEX

Explanations

numerical data or values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

-0.17

enser

-0.15

chos

-0.14

 Strom

-0.14

kÃ¶

-0.14

ROUT

-0.14

boro

-0.13

_REDIRECT

-0.13

 Stern

-0.13

kim

-0.13

POSITIVE LOGITS

0.23

0.21

0.17

olley

0.17

0.15

ymb

0.15

Activations Density 0.069%

numerical data or values

No Comments

No Known Activations