INDEX

Explanations

programming language elements and function definitions in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

-0.15

em

-0.14

Kag

-0.14

ept

-0.14

 pist

-0.14

let

-0.13

 regards

-0.13

POSITIVE LOGITS

orf

0.17

/errors

0.16

 addCriterion

0.16

ãİ¡

0.15

å¸¯

0.15

chia

0.15

yth

0.15

_EV

0.14

=Value

0.14

astics

0.14

Activations Density 0.027%

programming language elements and function definitions in code

No Comments

No Known Activations