INDEX

Explanations

terms related to presidential elections and candidates

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

-0.19

imar

-0.17

kn

-0.16

Ø±ÙĪØª

-0.15

IMA

-0.15

 McCabe

-0.15

olem

-0.14

ogn

-0.14

Spo

-0.14

lege

-0.14

POSITIVE LOGITS

ÅĻiv

0.16

ãĥ«ãĥī

0.15

ompiler

0.15

½

0.14

bble

0.14

utto

0.14

ãĤŃãĥ¥

0.14

etur

0.13

mee

0.13

isci

0.13

Activations Density 0.004%

terms related to presidential elections and candidates

No Comments

No Known Activations