INDEX

Explanations

code-related terms and function calls within 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

Cs

-0.15

ENV

-0.14

adora

-0.14

 unprotected

-0.13

ÑĭÐ»

-0.13

oby

-0.13

/MIT

-0.13

iban

-0.13

VERTISE

-0.13

POSITIVE LOGITS

urette

0.15

ãĥ¼ãĥĢ

0.15

ije

0.14

amp

0.14

ej

0.14

.simps

0.14

COLUMN

0.14

 Latter

0.14

levator

0.14

iances

0.14

Activations Density 0.944%

code-related terms and function calls within programming context

No Comments

No Known Activations