INDEX

Explanations

verbs and their various inflections that indicate action or change

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

cia

-0.15

Å¾iv

-0.15

ilik

-0.15

leston

-0.15

$$$$

-0.14

gewater

-0.14

idades

-0.14

ught

-0.14

ÑĥÑĢÐ³

-0.14

 Breath

-0.14

POSITIVE LOGITS

roje

0.16

0.14

echa

0.14

rok

0.14

ott

0.14

.Euler

0.14

WARDED

0.13

 Pond

0.13

HOOK

0.13

Activations Density 0.208%

verbs and their various inflections that indicate action or change

No Comments

No Known Activations