INDEX

Explanations

terms related to consequences and their magnitude in historical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

fell

-0.17

LU

-0.15

dess

-0.15

fir

-0.15

roe

-0.15

uzzi

-0.15

olla

-0.14

 Rays

-0.14

 foreign

-0.14

estr

-0.14

POSITIVE LOGITS

StackSize

0.15

Ã±as

0.15

 aver

0.15

 Mikhail

0.15

VENTORY

0.15

embali

0.14

imore

0.14

eras

0.14

.dimensions

0.14

ASON

0.14

Activations Density 0.071%

terms related to consequences and their magnitude in historical contexts

No Comments

No Known Activations