INDEX

Explanations

names and familial connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

Bij

-0.14

 Guar

-0.13

hong

-0.13

ITTE

-0.13

_EDEFAULT

-0.13

iagnostics

-0.13

nell

-0.13

ÏĦÎ¹Î½

-0.13

DeviceInfo

-0.13

 Rena

-0.12

POSITIVE LOGITS

ibold

0.18

ofilm

0.15

ques

0.14

fono

0.14

iska

0.13

ÑĸÐºÐ°

0.13

Ih

0.13

 ÑĢÐ°Ð¹

0.13

ocado

0.13

Activations Density 0.059%

names and familial connections

No Comments

No Known Activations