INDEX

Explanations

connectors and phrases that indicate relationships, conditions, or sequences in thoughts and actions

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

ians

-0.14

 consent

-0.14

 VARIABLES

-0.13

hwnd

-0.13

 mote

-0.13

ÐµÐ²Ð¸

-0.13

_IMPORTED

-0.13

ÑĥÐ´Ð¸

-0.13

utterstock

-0.13

POSITIVE LOGITS

nun

0.15

ctp

0.14

endum

0.14

ãĥ³ãĤº

0.13

_TS

0.13

quote

0.13

endas

0.13

 Ding

0.13

stellen

0.13

å¾

0.13

Activations Density 0.110%

connectors and phrases that indicate relationships, conditions, or sequences in thoughts and actions

No Comments

No Known Activations