INDEX

Explanations

references to grass and vegetation in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

.jsp

-0.17

phans

-0.16

ondo

-0.15

agnar

-0.15

werp

-0.15

ISE

-0.15

moire

-0.14

 èŃ

-0.14

ipple

-0.14

POSITIVE LOGITS

 growing

0.20

aceous

0.18

-growing

0.18

lew

0.16

ery

0.15

ÏĥÎºÎµ

0.15

AREST

0.15

Growing

0.14

dio

0.14

 grown

0.14

Activations Density 0.139%

references to grass and vegetation in various contexts

No Comments

No Known Activations