INDEX

Explanations

terms related to wood and its various forms or uses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

orative

-0.15

uses

-0.15

ouncer

-0.15

itte

-0.14

asing

-0.14

memberOf

-0.14

ãĥ£

-0.14

ucci

-0.14

stances

-0.13

 noqa

-0.13

POSITIVE LOGITS

shed

0.16

asley

0.16

ãĤ¥

0.15

bine

0.15

à¯įà®

0.15

oh

0.15

erner

0.15

oya

0.15

oser

0.14

chip

0.14

Activations Density 0.029%

terms related to wood and its various forms or uses

No Comments

No Known Activations