INDEX

Explanations

terms related to various types of apparatus or equipment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

aille

-0.17

erable

-0.16

oma

-0.16

gos

-0.15

etto

-0.15

lej

-0.15

ighton

-0.15

gan

-0.15

 Architects

-0.14

ĨĴ

-0.14

POSITIVE LOGITS

ilt

0.15

.Sdk

0.15

_codegen

0.15

ç¢¼

0.14

ÙĤÙĬ

0.14

 puberty

0.14

ako

0.14

 tard

0.14

alar

0.13

umba

0.13

Activations Density 0.010%

terms related to various types of apparatus or equipment

No Comments

No Known Activations