INDEX

Explanations

references to high quality across various contexts

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

lang

-0.15

 Pill

-0.14

heid

-0.14

aira

-0.14

ElementException

-0.13

oru

-0.13

-pill

-0.13

aus

-0.13

kim

-0.13

 delayed

-0.13

POSITIVE LOGITS

eum

0.19

0.17

Ð°Ð½Ð¸ÑĨ

0.16

ilar

0.15

plib

0.15

 Strauss

0.15

FirstChild

0.14

atak

0.14

PACE

0.14

pong

0.14

Activations Density 0.021%

references to high quality across various contexts

No Comments

No Known Activations