INDEX

Explanations

numerical data or references in scientific contexts, especially those related to measurements or identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

EMON

-0.16

 åı¸

-0.15

à¸ĵ

-0.14

mess

-0.14

iem

-0.14

urette

-0.14

sat

-0.14

 Pioneer

-0.14

acades

-0.14

Fat

-0.13

POSITIVE LOGITS

endale

0.16

RESET

0.15

GRA

0.15

.readValue

0.14

oeff

0.14

 Boundary

0.13

æ¼ı

0.13

OrElse

0.13

arden

0.13

unlink

0.13

Activations Density 0.027%

numerical data or references in scientific contexts, especially those related to measurements or identifiers

No Comments

No Known Activations