INDEX

Explanations

terms related to documentation and technical manuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

tam

-0.15

orns

-0.15

 Archives

-0.14

çĹ

-0.14

Moy

-0.14

(IntPtr

-0.14

rij

-0.14

MAC

-0.14

adder

-0.14

Tam

-0.13

POSITIVE LOGITS

doc

0.18

/documentation

0.17

doc

0.17

 docs

0.17

 technical

0.16

 document

0.16

 guides

0.15

 ifndef

0.15

 Annunci

0.15

Doc

0.15

Activations Density 0.059%

terms related to documentation and technical manuals

No Comments

No Known Activations