INDEX

Explanations

coding commands and file management instructions related to programming frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 shrink

-0.15

ROTO

-0.14

PC

-0.14

 operating

-0.14

ex

-0.14

 Stick

-0.14

sc

-0.14

 Globe

-0.14

ãĥ³ãĥĩãĤ£

-0.14

untime

-0.14

POSITIVE LOGITS

 Incontri

0.17

enz

0.16

lund

0.16

nnen

0.16

erra

0.15

ligt

0.15

ORA

0.14

vsp

0.14

riday

0.14

 offsetof

0.14

Activations Density 0.401%

coding commands and file management instructions related to programming frameworks

No Comments

No Known Activations