INDEX

Explanations

references to academic research and research-related positions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

oud

-0.15

eton

-0.15

lar

-0.15

Å¾iv

-0.15

odo

-0.14

 è³

-0.14

kontakte

-0.14

argins

-0.14

essim

-0.14

ace

-0.14

POSITIVE LOGITS

inne

0.14

ellen

0.14

ê·¼

0.14

/banner

0.14

 eccentric

0.13

 CONSEQUENTIAL

0.13

Sky

0.13

arm

0.13

 SKIP

0.13

sky

0.13

Activations Density 0.034%

references to academic research and research-related positions

No Comments

No Known Activations