INDEX

Explanations

dates mentioned in the text

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

velt

-0.17

Ð¾ÑĢÐ´

-0.15

IDAD

-0.15

izable

-0.15

iegel

-0.14

IZER

-0.14

ldr

-0.14

à¸Ĥ

-0.13

Synopsis

-0.13

POSITIVE LOGITS

.,

0.19

oner

0.18

ub

0.18

Sept

0.16

 Sept

0.16

.).↵↵

0.15

ual

0.15

-Oct

0.15

./

0.15

Activations Density 0.022%

dates mentioned in the text

No Comments

No Known Activations