INDEX

Explanations

verbs indicating the initiation of actions or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

Continue

-0.17

 continuing

-0.17

 continue

-0.16

 continuation

-0.16

continue

-0.16

 Continue

-0.16

 toujours

-0.16

 Continuing

-0.15

still

-0.15

ç»§ç»Ń

-0.15

POSITIVE LOGITS

to

0.16

(ed

0.16

0.15

 down

0.15

avenport

0.15

pace

0.14

 another

0.14

 exert

0.14

/feed

0.14

Activations Density 0.061%

verbs indicating the initiation of actions or processes

No Comments

No Known Activations