INDEX

Explanations

terms related to classification and evaluation of categories or standards

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

uzzer

-0.14

Ð½Ð°ÑĤ

-0.14

çģ

-0.14

abilit

-0.14

stown

-0.14

monton

-0.13

/application

-0.13

.Skip

-0.13

ibus

-0.13

Ø¯Ùħ

-0.13

POSITIVE LOGITS

.ov

0.16

 âĢķ

0.15

ewith

0.15

 Corner

0.15

InstanceId

0.14

 Bout

0.14

chu

0.14

Scaler

0.14

Activations Density 0.085%

terms related to classification and evaluation of categories or standards

No Comments

No Known Activations