INDEX

Explanations

mentions of rules, requirements, or suggestions regarding what to bring and how to prepare for events or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

inning

-0.16

enzhen

-0.15

Stamped

-0.14

redient

-0.14

illard

-0.14

iro

-0.14

IVO

-0.13

reh

-0.13

=(-

-0.13

ensed

-0.13

POSITIVE LOGITS

 bring

0.70

 bringing

0.65

 Bring

0.63

Bring

0.63

bring

0.63

 brings

0.61

 brought

0.60

bringing

0.59

å¸¦

0.50

 Bringing

0.48

Activations Density 0.351%

mentions of rules, requirements, or suggestions regarding what to bring and how to prepare for events or situations

No Comments

No Known Activations