INDEX

Explanations

historical references and related events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

VERTISE

-0.17

 addCriterion

-0.16

 groÃŁen

-0.15

ãģĹãĤĩãģĨ

-0.14

elier

-0.14

VERRIDE

-0.14

 ÐºÐ¾ÑĤÐ¾ÑĢÐ¾Ð³Ð¾

-0.14

dur

-0.14

 benÃ¶t

-0.14

ollar

-0.13

POSITIVE LOGITS

 member

0.18

 Member

0.18

 Teil

0.17

abei

0.17

ABL

0.16

 since

0.16

 part

0.14

Member

0.14

 recipient

0.14

ouns

0.14

Activations Density 0.050%

historical references and related events

No Comments

No Known Activations