INDEX

Explanations

fragments of code and programming structure elements

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

stoup

-0.17

Å¡li

-0.16

enef

-0.16

stoupil

-0.16

;element

-0.16

.Annotations

-0.16

ERY

-0.15

SCALL

-0.15

enen

-0.15

uell

-0.14

POSITIVE LOGITS

ãĥ³ãĥĶ

0.17

ophobic

0.16

Lud

0.14

 yellow

0.14

 Chain

0.14

ori

0.14

Detach

0.14

lap

0.14

dom

0.13

Activations Density 0.262%

fragments of code and programming structure elements

No Comments

No Known Activations