INDEX

Explanations

names of individuals, particularly in familial or genealogical 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

licht

-0.19

athers

-0.16

ynes

-0.15

eder

-0.15

riere

-0.14

Ð¾ÑĩÐ½Ð¾

-0.14

alers

-0.14

tam

-0.14

ÏĦÏİÎ½

-0.13

 McConnell

-0.13

POSITIVE LOGITS

izr

0.15

Ø¨ÙĬØ±Ø©

0.15

omal

0.15

idor

0.14

Ð¿Ð°ÑĤ

0.14

Sus

0.14

ritten

0.13

æ£Ģ

0.13

_trap

0.13

orris

0.13

Activations Density 0.159%

names of individuals, particularly in familial or genealogical contexts

No Comments

No Known Activations