INDEX

Explanations

technical terms related to formal models and semantics in systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

unm

-0.15

-0.14

ty

-0.14

Nah

-0.13

 scal

-0.13

sei

-0.13

rap

-0.13

 Continental

-0.13

unks

-0.13

POSITIVE LOGITS

 States

0.20

 BÃ¼

0.19

States

0.19

 Reach

0.18

 Ziel

0.18

 transitions

0.18

StateMachine

0.18

transition

0.17

.states

0.17

 Transition

0.17

Activations Density 0.056%

technical terms related to formal models and semantics in systems

No Comments

No Known Activations