INDEX

Explanations

occurrences of significant verbs and action-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

Ä±lÄ±Ã§

-0.14

acco

-0.13

cret

-0.13

serve

-0.13

ãĢħ

-0.13

Äįek

-0.13

 crews

-0.12

INGS

-0.12

ÑĩÐºÐ¸

-0.12

PTR

-0.12

POSITIVE LOGITS

datatable

0.14

.dtd

0.14

\common

0.14

pton

0.14

 Stretch

0.13

 Undert

0.13

 Rosenberg

0.13

aurus

0.13

aat

0.13

Activations Density 0.357%

occurrences of significant verbs and action-related terms

No Comments

No Known Activations

occurrences of significant verbs and action-related terms

No Comments

No Known Activations