INDEX

Explanations

references to academic publications and medical journals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ATTER

-0.15

rozen

-0.15

 addCriterion

-0.15

fsp

-0.14

uzzle

-0.14

otten

-0.14

atk

-0.14

/*@

-0.14

alis

-0.14

atters

-0.14

POSITIVE LOGITS

0.17

 OnTrigger

0.13

mot

0.13

ibur

0.13

 tide

0.13

 proof

0.13

 Sabb

0.13

ENA

0.13

pur

0.13

 Rouge

0.13

Activations Density 0.008%

references to academic publications and medical journals

No Comments

No Known Activations