INDEX

Explanations

mentions of articles, reports, or stories that are complete and available for reading

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

UMAN

-0.14

 Subscription

-0.14

 Behavior

-0.13

-placeholder

-0.13

erno

-0.13

zte

-0.13

 Creature

-0.13

elin

-0.13

 Sight

-0.13

 Serial

-0.13

POSITIVE LOGITS

LastError

0.17

unce

0.15

Glyph

0.15

iger

0.14

DSL

0.14

itter

0.14

zych

0.14

tas

0.14

oe

0.13

oft

0.13

Activations Density 0.014%

mentions of articles, reports, or stories that are complete and available for reading

No Comments

No Known Activations