INDEX

Explanations

key concepts or terms that indicate important elements related to definitions, classifications, or structures

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

iu

-0.16

ocal

-0.15

-Cal

-0.15

 Wyatt

-0.14

ru

-0.14

-0.13

amente

-0.13

estatus

-0.13

od

-0.13

POSITIVE LOGITS

umu

0.16

ogue

0.16

indre

0.15

ãĥ³ãĥĪ

0.15

ICODE

0.15

Ø§Ø³Ø±

0.14

ittal

0.14

atte

0.14

dorf

0.14

icare

0.13

Activations Density 0.008%

key concepts or terms that indicate important elements related to definitions, classifications, or structures

No Comments

No Known Activations