INDEX

Explanations

words related to specific cultural or historical references

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

aler

-0.16

onis

-0.15

oky

-0.15

zure

-0.15

nesc

-0.15

ozo

-0.15

 Trident

-0.14

onec

-0.14

annotate

-0.14

orum

-0.14

POSITIVE LOGITS

olson

0.18

oll

0.17

zsche

0.17

olas

0.16

 Hoover

0.16

gro

0.16

olina

0.15

Altern

0.15

astle

0.14

eneg

0.14

Activations Density 0.047%

words related to specific cultural or historical references

No Comments

No Known Activations