INDEX

Explanations

names of characters in film and television productions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

tainment

-0.17

Civ

-0.16

Ð»ÑıÑħ

-0.15

ONTAL

-0.15

liqu

-0.15

bler

-0.15

asher

-0.15

latex

-0.15

ensa

-0.14

/Dk

-0.14

POSITIVE LOGITS

agg

0.16

ii

0.16

ordova

0.15

à¤¾à¤°à¤ķ

0.14

icontrol

0.13

iiii

0.13

ji

0.13

 Survivor

0.13

suppress

0.13

 survivor

0.13

Activations Density 0.007%

names of characters in film and television productions

No Comments

No Known Activations