INDEX

Explanations

information related to quantifiable metrics and specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

auen

-0.16

 Gins

-0.16

CEED

-0.15

ÙĤØ¨

-0.15

reso

-0.14

Ã¡i

-0.14

ede

-0.14

hunter

-0.14

esp

-0.13

 Ø§ÙĦØ¹ÙĨ

-0.13

POSITIVE LOGITS

Neb

0.16

ziel

0.15

Emb

0.14

ãĤ¦ãĥ³

0.14

RITE

0.14

assi

0.14

 Budget

0.14

ancia

0.14

ayout

0.13

è¦ª

0.13

Activations Density 0.110%

information related to quantifiable metrics and specifications

No Comments

No Known Activations