INDEX

Explanations

occurrences of complex phrases within a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ucci

-0.17

ej

-0.16

captures

-0.15

Ð¾Ð¼ÐµÑĢ

-0.15

isko

-0.15

rame

-0.14

mini

-0.14

loh

-0.14

uge

-0.14

Giz

-0.14

POSITIVE LOGITS

apon

0.16

aus

0.16

0.15

 McCabe

0.14

ires

0.14

ird

0.14

 testName

0.14

Activations Density 0.005%

occurrences of complex phrases within a technical context

No Comments

No Known Activations