INDEX

Explanations

terms related to cable television and related services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ernel

-0.17

fov

-0.16

ippets

-0.14

ENDOR

-0.14

ances

-0.14

è§

-0.14

ubi

-0.14

svn

-0.14

otas

-0.13

mai

-0.13

POSITIVE LOGITS

istar

0.17

uke

0.15

ebe

0.15

arch

0.14

vise

0.13

ãĤĪãģĨ

0.13

ÑĤÑı

0.13

 Forces

0.13

Began

0.13

gt

0.13

Activations Density 0.008%

terms related to cable television and related services

No Comments

No Known Activations