INDEX

Explanations

infinitive forms of verbs indicating purpose or intent

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

ording

-0.15

azen

-0.15

rippling

-0.14

roit

-0.14

avern

-0.14

IRT

-0.14

Ñī

-0.14

reme

-0.14

lets

-0.13

jk

-0.13

POSITIVE LOGITS

 constitution

0.15

wed

0.15

ssel

0.13

inka

0.13

Ð²Ð°Ð´

0.13

Reviewed

0.13

igel

0.13

hle

0.13

oust

0.12

 juice

0.12

Activations Density 0.074%

infinitive forms of verbs indicating purpose or intent

No Comments

No Known Activations