INDEX

Explanations

sequences of numerical values, particularly those related to legal or regulatory documents

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ponible

-0.15

 norge

-0.15

bro

-0.14

heet

-0.14

zeigen

-0.14

 wings

-0.14

iom

-0.13

EMPL

-0.13

asel

-0.13

IFIER

-0.13

POSITIVE LOGITS

ãĥĬãĥ«

0.15

ãĤ¤ãĥ³ãĥĪ

0.15

çĳ

0.14

_COMPAT

0.14

vb

0.14

pkt

0.14

trees

0.13

 Scal

0.13

ared

0.13

 ?><?

0.13

Activations Density 0.028%

sequences of numerical values, particularly those related to legal or regulatory documents

No Comments

No Known Activations