INDEX

Explanations

terms related to technical and structured processes or elements in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

orb

-0.16

dech

-0.16

habi

-0.16

ä¸Ģä¸ªäºº

-0.16

lej

-0.16

 Cutter

-0.15

mayan

-0.15

å¶

-0.15

ode

-0.14

usch

-0.14

POSITIVE LOGITS

resse

0.15

ght

0.15

CAP

0.14

 blankets

0.14

mol

0.14

LAT

0.14

@ResponseBody

0.14

 Crimes

0.13

CAP

0.13

AG

0.13

Activations Density 0.033%

terms related to technical and structured processes or elements in various contexts

No Comments

No Known Activations