INDEX

Explanations

terms related to technical or legal language, particularly in equations and claims

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ohan

-0.16

Ð¾Ñı

-0.16

ÑĢÐ¾Ð´

-0.15

Ñľ

-0.15

ForRow

-0.15

uars

-0.14

 Clarke

-0.14

ysz

-0.14

usi

-0.14

monds

-0.14

POSITIVE LOGITS

lap

0.16

ibri

0.16

moz

0.15

roid

0.15

ocz

0.15

unto

0.15

ius

0.14

uder

0.14

aph

0.14

ios

0.14

Activations Density 0.000%

terms related to technical or legal language, particularly in equations and claims

No Comments

No Known Activations