INDEX

Explanations

key characters and symbols that indicate code or programming elements

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

rapper

-0.16

rer

-0.15

abh

-0.15

ever

-0.14

Bun

-0.13

CCR

-0.13

ynamo

-0.13

è²

-0.13

aan

-0.13

ekk

-0.13

POSITIVE LOGITS

ItemSelectedListener

0.15

CERT

0.15

omba

0.14

ResponseStatus

0.14

immel

0.14

etz

0.14

ares

0.14

Kut

0.14

 Trend

0.14

iel

0.13

Activations Density 0.031%

key characters and symbols that indicate code or programming elements

No Comments

No Known Activations