INDEX

Explanations

components related to configuration or code snippets in a programming context

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

dz

-0.15

sian

-0.15

atform

-0.15

radi

-0.15

/dat

-0.14

 Tear

-0.14

anke

-0.14

wand

-0.14

ica

-0.13

ãĥĬãĥ«

-0.13

POSITIVE LOGITS

æ¢

0.17

lang

0.16

esh

0.16

fir

0.15

Jay

0.15

Jay

0.15

owan

0.14

uh

0.14

OnError

0.14

lij

0.14

Activations Density 0.089%

components related to configuration or code snippets in a programming context

No Comments

No Known Activations